Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    adjectives and nouns related to the natural environment

    oai_token-act-pair · gpt-3.5-turbo

    references to different components or aspects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburgh
    -0.87
    BI
    -0.68
    use
    -0.67
    ceed
    -0.67
    ble
    -0.65
    shut
    -0.63
    ller
    -0.62
    claimed
    -0.61
    king
    -0.61
     Telegraph
    -0.61
    POSITIVE LOGITS
     elements
    1.53
     element
    1.26
     guiActiveUn
    0.86
    osaurs
    0.86
    aea
    0.85
     Elements
    0.82
     layers
    0.80
     components
    0.79
     abund
    0.78
     Element
    0.77
    Act Density 0.010%

    No Known Activations